collaborators

11 papers

cs.CV2026

PathRelax: Parallel-Path Relaxed Speculative Jacobi Decoding for Accelerating Auto-Regressive Text-to-Image Generation

Haodong Lei, Hongsong Wang, Bingxuan Dai +1

The growing need for high-resolution image generation in autoregressive text-to-image models has resulted in extended token sequences, significantly increasing computational costs…

cs.CL2026

Benchmarking Gaslighting Attacks Against Speech Large Language Models

Jinyang Wu, Bin Zhu, Xiandong Zou +3

As Speech Large Language Models (Speech LLMs) become increasingly integrated into voice-based applications, ensuring their robustness against manipulative or adversarial input beco…

cs.CV2026

Bilingual Text-to-Motion Generation: A New Benchmark and Baselines

Wanjiang Weng, Xiaofeng Tan, Xiangbo Shu +3

Text-to-motion generation holds significant potential for cross-linguistic applications, yet it is hindered by the lack of bilingual datasets and the poor cross-lingual semantic un…

cs.CV2026

DreamCS: Geometry-Aware Text-to-3D Generation with Unpaired 3D Reward Supervision

Xiandong Zou, Ruihao Xia, Hongsong Wang +1

While text-to-3D generation has attracted growing interest, existing methods often struggle to produce 3D assets that align well with human preferences. Current preference alignmen…

cs.AI2026

HPS: Hard Preference Sampling for Human Preference Alignment

Xiandong Zou, Wanyu Lin, Yuchen Li +1

Aligning Large Language Model (LLM) responses with human preferences is vital for building safe and controllable AI systems. While preference optimization methods based on Plackett…

cs.CV2026

Dragging with Geometry: From Pixels to Geometry-Guided Image Editing

Xinyu Pu, Hongsong Wang, Jie Gui +1

Interactive point-based image editing serves as a controllable editor, enabling precise and flexible manipulation of image content. However, most drag-based methods operate primari…